# Solving HJB PDE using deep learning

**URL:** <https://discourse.julialang.org/t/solving-hjb-pde-using-deep-learning/60639>\
**Category:** Numerics\
**Tags:** economics, pde\
**Created:** [May 6, 2021, 10:35am UTC](https://discourse.julialang.org/t/solving-hjb-pde-using-deep-learning/60639 "2021-05-06T10:35:48Z")\
**Posts on this page:** 1\
**Showing post:** 12

<div class="post-metadata">

**Author:** ![Goosee](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/goosee/32/31000_2.png) [@Goosee](https://discourse.julialang.org/u/Goosee)\
**Post date:** [December 18, 2021, 3:31am UTC](https://discourse.julialang.org/t/solving-hjb-pde-using-deep-learning/60639/12 "2021-12-18T03:31:03Z")

</div>

Hi everyone!

I recently started using Julia and joined this forum precisely because of this issue. I managed to solve the neoclassical growth model with Julia’s NeuralPDE. I am not sure if I have done this in an efficient manner, but it works.

Here is a link with the code and a brief note: [https://github.com/GMellior/NGM\_neuralnetwork](https://github.com/GMellior/NGM_neuralnetwork)

While I find that the code above worked for this specific model I have not been able to scale up to more complex versions, say by adding a diffusion in productivity or more state variables.

---

_[View the full topic](https://discourse.julialang.org/t/solving-hjb-pde-using-deep-learning/60639)._